© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117673
    Prev
    Next
    INDEX
    Explanations

    digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     достаточно
    -0.07
    ALE
    -0.06
    最多的
    -0.06
     restent
    -0.06
     столько
    -0.06
    沭
    -0.06
     TNumber
    -0.06
     podemos
    -0.06
     जैसे
    -0.06
     hintergrund
    -0.06
    POSITIVE LOGITS
     those
    0.06
     It
    0.06
     This
    0.06
     suited
    0.06
     entrepreneurs
    0.06
     employs
    0.06
    All
    0.06
     circunstancias
    0.06
     includes
    0.05
    molecular
    0.05
    Activations Density 0.021%

    No Known Activations